File size: 17,469 Bytes
a6dac9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
""" Inception-V3

Originally from torchvision Inception3 model
Licensed BSD-Clause 3 https://github.com/pytorch/vision/blob/master/LICENSE
"""
import torch
import torch.nn as nn
import torch.nn.functional as F

from timm.data import IMAGENET_DEFAULT_STD, IMAGENET_DEFAULT_MEAN, IMAGENET_INCEPTION_MEAN, IMAGENET_INCEPTION_STD
from .helpers import build_model_with_cfg
from .registry import register_model
from .layers import trunc_normal_, create_classifier, Linear


def _cfg(url='', **kwargs):
    return {
        'url': url,
        'num_classes': 1000, 'input_size': (3, 299, 299), 'pool_size': (8, 8),
        'crop_pct': 0.875, 'interpolation': 'bicubic',
        'mean': IMAGENET_INCEPTION_MEAN, 'std': IMAGENET_INCEPTION_STD,
        'first_conv': 'Conv2d_1a_3x3.conv', 'classifier': 'fc',
        **kwargs
    }


default_cfgs = {
    # original PyTorch weights, ported from Tensorflow but modified
    'inception_v3': _cfg(
        url='https://download.pytorch.org/models/inception_v3_google-1a9a5a14.pth',
        has_aux=True),  # checkpoint has aux logit layer weights
    # my port of Tensorflow SLIM weights (http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz)
    'tf_inception_v3': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_inception_v3-e0069de4.pth',
        num_classes=1000, has_aux=False, label_offset=1),
    # my port of Tensorflow adversarially trained Inception V3 from
    # http://download.tensorflow.org/models/adv_inception_v3_2017_08_18.tar.gz
    'adv_inception_v3': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/adv_inception_v3-9e27bd63.pth',
        num_classes=1000, has_aux=False, label_offset=1),
    # from gluon pretrained models, best performing in terms of accuracy/loss metrics
    # https://gluon-cv.mxnet.io/model_zoo/classification.html
    'gluon_inception_v3': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/gluon_inception_v3-9f746940.pth',
        mean=IMAGENET_DEFAULT_MEAN,  # also works well with inception defaults
        std=IMAGENET_DEFAULT_STD,  # also works well with inception defaults
        has_aux=False,
    )
}


class InceptionA(nn.Module):

    def __init__(self, in_channels, pool_features, conv_block=None):
        super(InceptionA, self).__init__()
        if conv_block is None:
            conv_block = BasicConv2d
        self.branch1x1 = conv_block(in_channels, 64, kernel_size=1)

        self.branch5x5_1 = conv_block(in_channels, 48, kernel_size=1)
        self.branch5x5_2 = conv_block(48, 64, kernel_size=5, padding=2)

        self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, padding=1)

        self.branch_pool = conv_block(in_channels, pool_features, kernel_size=1)

    def _forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionB(nn.Module):

    def __init__(self, in_channels, conv_block=None):
        super(InceptionB, self).__init__()
        if conv_block is None:
            conv_block = BasicConv2d
        self.branch3x3 = conv_block(in_channels, 384, kernel_size=3, stride=2)

        self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, stride=2)

    def _forward(self, x):
        branch3x3 = self.branch3x3(x)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)

        outputs = [branch3x3, branch3x3dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionC(nn.Module):

    def __init__(self, in_channels, channels_7x7, conv_block=None):
        super(InceptionC, self).__init__()
        if conv_block is None:
            conv_block = BasicConv2d
        self.branch1x1 = conv_block(in_channels, 192, kernel_size=1)

        c7 = channels_7x7
        self.branch7x7_1 = conv_block(in_channels, c7, kernel_size=1)
        self.branch7x7_2 = conv_block(c7, c7, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7_3 = conv_block(c7, 192, kernel_size=(7, 1), padding=(3, 0))

        self.branch7x7dbl_1 = conv_block(in_channels, c7, kernel_size=1)
        self.branch7x7dbl_2 = conv_block(c7, c7, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7dbl_3 = conv_block(c7, c7, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7dbl_4 = conv_block(c7, c7, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7dbl_5 = conv_block(c7, 192, kernel_size=(1, 7), padding=(0, 3))

        self.branch_pool = conv_block(in_channels, 192, kernel_size=1)

    def _forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch7x7 = self.branch7x7_1(x)
        branch7x7 = self.branch7x7_2(branch7x7)
        branch7x7 = self.branch7x7_3(branch7x7)

        branch7x7dbl = self.branch7x7dbl_1(x)
        branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionD(nn.Module):

    def __init__(self, in_channels, conv_block=None):
        super(InceptionD, self).__init__()
        if conv_block is None:
            conv_block = BasicConv2d
        self.branch3x3_1 = conv_block(in_channels, 192, kernel_size=1)
        self.branch3x3_2 = conv_block(192, 320, kernel_size=3, stride=2)

        self.branch7x7x3_1 = conv_block(in_channels, 192, kernel_size=1)
        self.branch7x7x3_2 = conv_block(192, 192, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7x3_3 = conv_block(192, 192, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7x3_4 = conv_block(192, 192, kernel_size=3, stride=2)

    def _forward(self, x):
        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)

        branch7x7x3 = self.branch7x7x3_1(x)
        branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_4(branch7x7x3)

        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
        outputs = [branch3x3, branch7x7x3, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionE(nn.Module):

    def __init__(self, in_channels, conv_block=None):
        super(InceptionE, self).__init__()
        if conv_block is None:
            conv_block = BasicConv2d
        self.branch1x1 = conv_block(in_channels, 320, kernel_size=1)

        self.branch3x3_1 = conv_block(in_channels, 384, kernel_size=1)
        self.branch3x3_2a = conv_block(384, 384, kernel_size=(1, 3), padding=(0, 1))
        self.branch3x3_2b = conv_block(384, 384, kernel_size=(3, 1), padding=(1, 0))

        self.branch3x3dbl_1 = conv_block(in_channels, 448, kernel_size=1)
        self.branch3x3dbl_2 = conv_block(448, 384, kernel_size=3, padding=1)
        self.branch3x3dbl_3a = conv_block(384, 384, kernel_size=(1, 3), padding=(0, 1))
        self.branch3x3dbl_3b = conv_block(384, 384, kernel_size=(3, 1), padding=(1, 0))

        self.branch_pool = conv_block(in_channels, 192, kernel_size=1)

    def _forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = [
            self.branch3x3_2a(branch3x3),
            self.branch3x3_2b(branch3x3),
        ]
        branch3x3 = torch.cat(branch3x3, 1)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = [
            self.branch3x3dbl_3a(branch3x3dbl),
            self.branch3x3dbl_3b(branch3x3dbl),
        ]
        branch3x3dbl = torch.cat(branch3x3dbl, 1)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionAux(nn.Module):

    def __init__(self, in_channels, num_classes, conv_block=None):
        super(InceptionAux, self).__init__()
        if conv_block is None:
            conv_block = BasicConv2d
        self.conv0 = conv_block(in_channels, 128, kernel_size=1)
        self.conv1 = conv_block(128, 768, kernel_size=5)
        self.conv1.stddev = 0.01
        self.fc = Linear(768, num_classes)
        self.fc.stddev = 0.001

    def forward(self, x):
        # N x 768 x 17 x 17
        x = F.avg_pool2d(x, kernel_size=5, stride=3)
        # N x 768 x 5 x 5
        x = self.conv0(x)
        # N x 128 x 5 x 5
        x = self.conv1(x)
        # N x 768 x 1 x 1
        # Adaptive average pooling
        x = F.adaptive_avg_pool2d(x, (1, 1))
        # N x 768 x 1 x 1
        x = torch.flatten(x, 1)
        # N x 768
        x = self.fc(x)
        # N x 1000
        return x


class BasicConv2d(nn.Module):

    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels, eps=0.001)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x, inplace=True)


class InceptionV3(nn.Module):
    """Inception-V3 with no AuxLogits
    FIXME two class defs are redundant, but less screwing around with torchsript fussyness and inconsistent returns
    """

    def __init__(self, num_classes=1000, in_chans=3, drop_rate=0., global_pool='avg', aux_logits=False):
        super(InceptionV3, self).__init__()
        self.num_classes = num_classes
        self.drop_rate = drop_rate
        self.aux_logits = aux_logits

        self.Conv2d_1a_3x3 = BasicConv2d(in_chans, 32, kernel_size=3, stride=2)
        self.Conv2d_2a_3x3 = BasicConv2d(32, 32, kernel_size=3)
        self.Conv2d_2b_3x3 = BasicConv2d(32, 64, kernel_size=3, padding=1)
        self.Pool1 = nn.MaxPool2d(kernel_size=3, stride=2)
        self.Conv2d_3b_1x1 = BasicConv2d(64, 80, kernel_size=1)
        self.Conv2d_4a_3x3 = BasicConv2d(80, 192, kernel_size=3)
        self.Pool2 = nn.MaxPool2d(kernel_size=3, stride=2)
        self.Mixed_5b = InceptionA(192, pool_features=32)
        self.Mixed_5c = InceptionA(256, pool_features=64)
        self.Mixed_5d = InceptionA(288, pool_features=64)
        self.Mixed_6a = InceptionB(288)
        self.Mixed_6b = InceptionC(768, channels_7x7=128)
        self.Mixed_6c = InceptionC(768, channels_7x7=160)
        self.Mixed_6d = InceptionC(768, channels_7x7=160)
        self.Mixed_6e = InceptionC(768, channels_7x7=192)
        if aux_logits:
            self.AuxLogits = InceptionAux(768, num_classes)
        else:
            self.AuxLogits = None
        self.Mixed_7a = InceptionD(768)
        self.Mixed_7b = InceptionE(1280)
        self.Mixed_7c = InceptionE(2048)
        self.feature_info = [
            dict(num_chs=64, reduction=2, module='Conv2d_2b_3x3'),
            dict(num_chs=192, reduction=4, module='Conv2d_4a_3x3'),
            dict(num_chs=288, reduction=8, module='Mixed_5d'),
            dict(num_chs=768, reduction=16, module='Mixed_6e'),
            dict(num_chs=2048, reduction=32, module='Mixed_7c'),
        ]

        self.num_features = 2048
        self.global_pool, self.fc = create_classifier(self.num_features, self.num_classes, pool_type=global_pool)

        for m in self.modules():
            if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
                stddev = m.stddev if hasattr(m, 'stddev') else 0.1
                trunc_normal_(m.weight, std=stddev)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def forward_preaux(self, x):
        # N x 3 x 299 x 299
        x = self.Conv2d_1a_3x3(x)
        # N x 32 x 149 x 149
        x = self.Conv2d_2a_3x3(x)
        # N x 32 x 147 x 147
        x = self.Conv2d_2b_3x3(x)
        # N x 64 x 147 x 147
        x = self.Pool1(x)
        # N x 64 x 73 x 73
        x = self.Conv2d_3b_1x1(x)
        # N x 80 x 73 x 73
        x = self.Conv2d_4a_3x3(x)
        # N x 192 x 71 x 71
        x = self.Pool2(x)
        # N x 192 x 35 x 35
        x = self.Mixed_5b(x)
        # N x 256 x 35 x 35
        x = self.Mixed_5c(x)
        # N x 288 x 35 x 35
        x = self.Mixed_5d(x)
        # N x 288 x 35 x 35
        x = self.Mixed_6a(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6b(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6c(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6d(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6e(x)
        # N x 768 x 17 x 17
        return x

    def forward_postaux(self, x):
        x = self.Mixed_7a(x)
        # N x 1280 x 8 x 8
        x = self.Mixed_7b(x)
        # N x 2048 x 8 x 8
        x = self.Mixed_7c(x)
        # N x 2048 x 8 x 8
        return x

    def forward_features(self, x):
        x = self.forward_preaux(x)
        x = self.forward_postaux(x)
        return x

    def get_classifier(self):
        return self.fc

    def reset_classifier(self, num_classes, global_pool='avg'):
        self.num_classes = num_classes
        self.global_pool, self.fc = create_classifier(self.num_features, self.num_classes, pool_type=global_pool)

    def forward(self, x):
        x = self.forward_features(x)
        x = self.global_pool(x)
        if self.drop_rate > 0:
            x = F.dropout(x, p=self.drop_rate, training=self.training)
        x = self.fc(x)
        return x


class InceptionV3Aux(InceptionV3):
    """InceptionV3 with AuxLogits
    """

    def __init__(self, num_classes=1000, in_chans=3, drop_rate=0., global_pool='avg', aux_logits=True):
        super(InceptionV3Aux, self).__init__(
            num_classes, in_chans, drop_rate, global_pool, aux_logits)

    def forward_features(self, x):
        x = self.forward_preaux(x)
        aux = self.AuxLogits(x) if self.training else None
        x = self.forward_postaux(x)
        return x, aux

    def forward(self, x):
        x, aux = self.forward_features(x)
        x = self.global_pool(x)
        if self.drop_rate > 0:
            x = F.dropout(x, p=self.drop_rate, training=self.training)
        x = self.fc(x)
        return x, aux


def _create_inception_v3(variant, pretrained=False, **kwargs):
    default_cfg = default_cfgs[variant]
    aux_logits = kwargs.pop('aux_logits', False)
    if aux_logits:
        assert not kwargs.pop('features_only', False)
        model_cls = InceptionV3Aux
        load_strict = default_cfg['has_aux']
    else:
        model_cls = InceptionV3
        load_strict = not default_cfg['has_aux']
    return build_model_with_cfg(
        model_cls, variant, pretrained,
        default_cfg=default_cfg,
        pretrained_strict=load_strict,
        **kwargs)


@register_model
def inception_v3(pretrained=False, **kwargs):
    # original PyTorch weights, ported from Tensorflow but modified
    model = _create_inception_v3('inception_v3', pretrained=pretrained, **kwargs)
    return model


@register_model
def tf_inception_v3(pretrained=False, **kwargs):
    # my port of Tensorflow SLIM weights (http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz)
    model = _create_inception_v3('tf_inception_v3', pretrained=pretrained, **kwargs)
    return model


@register_model
def adv_inception_v3(pretrained=False, **kwargs):
    # my port of Tensorflow adversarially trained Inception V3 from
    # http://download.tensorflow.org/models/adv_inception_v3_2017_08_18.tar.gz
    model = _create_inception_v3('adv_inception_v3', pretrained=pretrained, **kwargs)
    return model


@register_model
def gluon_inception_v3(pretrained=False, **kwargs):
    # from gluon pretrained models, best performing in terms of accuracy/loss metrics
    # https://gluon-cv.mxnet.io/model_zoo/classification.html
    model = _create_inception_v3('gluon_inception_v3', pretrained=pretrained, **kwargs)
    return model